Multimodal fusion of radio-pathology and proteogenomics identify integrated glioma subtypes with prognostic and therapeutic opportunities
Abstract Integrating multimodal data can uncover causal features hidden in single-modality analyses, offering a comprehensive understanding of disease complexity. This study introduces a multimodal fusion subtyping (MOFS) framework that integrates radiological, pathological, genomic, transcriptomic,...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-58675-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849737460849836032 |
|---|---|
| author | Zaoqu Liu Yushuai Wu Hui Xu Minkai Wang Siyuan Weng Dongling Pei Shuang Chen WeiWei Wang Jing Yan Li Cui Jingxian Duan Yuanshen Zhao Zilong Wang Zeyu Ma Ran Li Wenchao Duan Yuning Qiu Dingyuan Su Sen Li Haoran Liu Wenyuan Li Caoyuan Ma Miaomiao Yu Yinhui Yu Te Chen Jing Fu YingWei Zhen Bin Yu Yuchen Ji Hairong Zheng Dong Liang Xianzhi Liu Dongming Yan Xinwei Han Fubing Wang Zhi-Cheng Li Zhenyu Zhang |
| author_facet | Zaoqu Liu Yushuai Wu Hui Xu Minkai Wang Siyuan Weng Dongling Pei Shuang Chen WeiWei Wang Jing Yan Li Cui Jingxian Duan Yuanshen Zhao Zilong Wang Zeyu Ma Ran Li Wenchao Duan Yuning Qiu Dingyuan Su Sen Li Haoran Liu Wenyuan Li Caoyuan Ma Miaomiao Yu Yinhui Yu Te Chen Jing Fu YingWei Zhen Bin Yu Yuchen Ji Hairong Zheng Dong Liang Xianzhi Liu Dongming Yan Xinwei Han Fubing Wang Zhi-Cheng Li Zhenyu Zhang |
| author_sort | Zaoqu Liu |
| collection | DOAJ |
| description | Abstract Integrating multimodal data can uncover causal features hidden in single-modality analyses, offering a comprehensive understanding of disease complexity. This study introduces a multimodal fusion subtyping (MOFS) framework that integrates radiological, pathological, genomic, transcriptomic, and proteomic data from 122 patients with IDH-wildtype adult glioma, identifying three subtypes: MOFS1 (proneural) with favorable prognosis, elevated neurodevelopmental activity, and abundant neurocyte infiltration; MOFS2 (proliferative) with the worst prognosis, superior proliferative activity, and genome instability; MOFS3 (TME-rich) with intermediate prognosis, abundant immune and stromal components, and sensitive to anti-PD-1 immunotherapy. STRAP emerges as a prognostic biomarker and potential therapeutic target for MOFS2, associated with its proliferative phenotype. Stromal infiltration in MOFS3 serves as a crucial prognostic indicator, allowing for further prognostic stratification. Additionally, we develop a deep neural network (DNN) classifier based on radiological features to further enhance the clinical translatability, providing a non-invasive tool for predicting MOFS subtypes. Overall, these findings highlight the potential of multimodal fusion in improving the classification, prognostic accuracy, and precision therapy of IDH-wildtype glioma, offering an avenue for personalized management. |
| format | Article |
| id | doaj-art-9f68f9d0684443b49917ae30c2fcf63c |
| institution | DOAJ |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-9f68f9d0684443b49917ae30c2fcf63c2025-08-20T03:06:54ZengNature PortfolioNature Communications2041-17232025-04-0116111810.1038/s41467-025-58675-9Multimodal fusion of radio-pathology and proteogenomics identify integrated glioma subtypes with prognostic and therapeutic opportunitiesZaoqu Liu0Yushuai Wu1Hui Xu2Minkai Wang3Siyuan Weng4Dongling Pei5Shuang Chen6WeiWei Wang7Jing Yan8Li Cui9Jingxian Duan10Yuanshen Zhao11Zilong Wang12Zeyu Ma13Ran Li14Wenchao Duan15Yuning Qiu16Dingyuan Su17Sen Li18Haoran Liu19Wenyuan Li20Caoyuan Ma21Miaomiao Yu22Yinhui Yu23Te Chen24Jing Fu25YingWei Zhen26Bin Yu27Yuchen Ji28Hairong Zheng29Dong Liang30Xianzhi Liu31Dongming Yan32Xinwei Han33Fubing Wang34Zhi-Cheng Li35Zhenyu Zhang36Department of Interventional Radiology, The First Affiliated Hospital of Zhengzhou UniversityShanghai Academy of Artificial Intelligence for ScienceDepartment of Interventional Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Interventional Radiology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityCenter of Reproductive Medicine, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Pathology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of MRI, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Pathology, The First Affiliated Hospital of Zhengzhou UniversityInstitute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesInstitute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversitySchool of Medicine, Hangzhou City UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityInstitute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesInstitute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Interventional Radiology, The First Affiliated Hospital of Zhengzhou UniversityCenter for Single-Cell Omics and Tumor Liquid Biopsy, Zhongnan Hospital of Wuhan UniversityInstitute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesDepartment of Neurosurgery, The First Affiliated Hospital of Zhengzhou UniversityAbstract Integrating multimodal data can uncover causal features hidden in single-modality analyses, offering a comprehensive understanding of disease complexity. This study introduces a multimodal fusion subtyping (MOFS) framework that integrates radiological, pathological, genomic, transcriptomic, and proteomic data from 122 patients with IDH-wildtype adult glioma, identifying three subtypes: MOFS1 (proneural) with favorable prognosis, elevated neurodevelopmental activity, and abundant neurocyte infiltration; MOFS2 (proliferative) with the worst prognosis, superior proliferative activity, and genome instability; MOFS3 (TME-rich) with intermediate prognosis, abundant immune and stromal components, and sensitive to anti-PD-1 immunotherapy. STRAP emerges as a prognostic biomarker and potential therapeutic target for MOFS2, associated with its proliferative phenotype. Stromal infiltration in MOFS3 serves as a crucial prognostic indicator, allowing for further prognostic stratification. Additionally, we develop a deep neural network (DNN) classifier based on radiological features to further enhance the clinical translatability, providing a non-invasive tool for predicting MOFS subtypes. Overall, these findings highlight the potential of multimodal fusion in improving the classification, prognostic accuracy, and precision therapy of IDH-wildtype glioma, offering an avenue for personalized management.https://doi.org/10.1038/s41467-025-58675-9 |
| spellingShingle | Zaoqu Liu Yushuai Wu Hui Xu Minkai Wang Siyuan Weng Dongling Pei Shuang Chen WeiWei Wang Jing Yan Li Cui Jingxian Duan Yuanshen Zhao Zilong Wang Zeyu Ma Ran Li Wenchao Duan Yuning Qiu Dingyuan Su Sen Li Haoran Liu Wenyuan Li Caoyuan Ma Miaomiao Yu Yinhui Yu Te Chen Jing Fu YingWei Zhen Bin Yu Yuchen Ji Hairong Zheng Dong Liang Xianzhi Liu Dongming Yan Xinwei Han Fubing Wang Zhi-Cheng Li Zhenyu Zhang Multimodal fusion of radio-pathology and proteogenomics identify integrated glioma subtypes with prognostic and therapeutic opportunities Nature Communications |
| title | Multimodal fusion of radio-pathology and proteogenomics identify integrated glioma subtypes with prognostic and therapeutic opportunities |
| title_full | Multimodal fusion of radio-pathology and proteogenomics identify integrated glioma subtypes with prognostic and therapeutic opportunities |
| title_fullStr | Multimodal fusion of radio-pathology and proteogenomics identify integrated glioma subtypes with prognostic and therapeutic opportunities |
| title_full_unstemmed | Multimodal fusion of radio-pathology and proteogenomics identify integrated glioma subtypes with prognostic and therapeutic opportunities |
| title_short | Multimodal fusion of radio-pathology and proteogenomics identify integrated glioma subtypes with prognostic and therapeutic opportunities |
| title_sort | multimodal fusion of radio pathology and proteogenomics identify integrated glioma subtypes with prognostic and therapeutic opportunities |
| url | https://doi.org/10.1038/s41467-025-58675-9 |
| work_keys_str_mv | AT zaoquliu multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT yushuaiwu multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT huixu multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT minkaiwang multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT siyuanweng multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT donglingpei multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT shuangchen multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT weiweiwang multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT jingyan multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT licui multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT jingxianduan multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT yuanshenzhao multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT zilongwang multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT zeyuma multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT ranli multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT wenchaoduan multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT yuningqiu multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT dingyuansu multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT senli multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT haoranliu multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT wenyuanli multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT caoyuanma multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT miaomiaoyu multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT yinhuiyu multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT techen multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT jingfu multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT yingweizhen multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT binyu multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT yuchenji multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT hairongzheng multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT dongliang multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT xianzhiliu multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT dongmingyan multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT xinweihan multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT fubingwang multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT zhichengli multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities AT zhenyuzhang multimodalfusionofradiopathologyandproteogenomicsidentifyintegratedgliomasubtypeswithprognosticandtherapeuticopportunities |